18 papers
Neuro-Symbolic Predicate Learning for Semantic Safe Robot Control
Zihan Ye, Jiayi Liu, Puze Liu +4
As robots are increasingly deployed in everyday environments, ensuring their safety has become a central challenge. Existing methods often encode safety requirements as opaque math…
ALDER: Discovering the Laws of a World by Acting in It
Teng Cao, Yu Deng, Quentin Delfosse +1
Reliable world models should not only predict future states but express how actions change the world in an explicit, transparent and testable form, such as equations. Yet methods t…
Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes
Hikaru Shindo, Yu Deng, Teng Cao +5
Interactive agents trained only against task return can achieve high scores while failing to represent the mechanisms that make their actions succeed. This makes brittle behavior d…
Kintsugi: Learning Policies by Repairing Executable Knowledge Bases
Teng Cao, Yu Deng, Hikaru Shindo +6
Modern embodied agents achieve impressive performance, but their task knowledge is often stored in neural weights, latent state, or prompt-bound memory, making individual policy kn…
Boosting deep Reinforcement Learning using pretraining with Logical Options
Zihan Ye, Phil Chau, Raban Emunds +5
Deep reinforcement learning agents are often misaligned, as they over-exploit early reward signals. Recently, several symbolic approaches have addressed these challenges by encodin…
Adaptable Hindsight Experience Replay for Search-Based Learning
Alexandros Vazaios, Jannis Brugger, Cedric Derstroff +2
AlphaZero-like Monte Carlo Tree Search systems, originally introduced for two-player games, dynamically balance exploration and exploitation using neural network guidance. This com…
STORM: Segment, Track, and Object Re-Localization from a Single Image
Yu Deng, Teng Cao, Hikaru Shindo +3
Accurate 6D pose estimation and tracking are core capabilities for physical AI systems, yet real-world deployment remains brittle and labor-intensive. Many pipelines rely on CAD mo…
Deep Reinforcement Learning Agents are not even close to Human Intelligence
Quentin Delfosse, Jannis Blüml, Fabian Tatai +6
Deep reinforcement learning (RL) agents achieve impressive results in a wide variety of tasks, but they lack zero-shot adaptation capabilities. While most robustness evaluations fo…
Better Decisions through the Right Causal World Model
Elisabeth Dillies, Quentin Delfosse, Jannis Blüml +3
Reinforcement learning (RL) agents have shown remarkable performances in various environments, where they can discover effective policies directly from sensory inputs. However, the…
Deep Reinforcement Learning via Object-Centric Attention
Jannis Blüml, Cedric Derstroff, Bjarne Gregori +3
Deep reinforcement learning agents, trained on raw pixel inputs, often fail to generalize beyond their training environments, relying on spurious correlations and irrelevant backgr…
ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding
Indraneil Paul, Haoyi Yang, Goran Glavaš +2
Language models (LMs) have become a staple of the code-writing toolbox. Their pre-training recipe has, however, remained stagnant over recent years, barring the occasional changes…
Polynomial Regret Concentration of UCB for Non-Deterministic State Transitions
Can Cömer, Jannis Blüml, Cedric Derstroff +1
Monte Carlo Tree Search (MCTS) has proven effective in solving decision-making problems in perfect information settings. However, its application to stochastic and imperfect inform…
Problem Solving Through Human-AI Preference-Based Cooperation
Subhabrata Dutta, Timo Kaufmann, Goran Glavaš +7
While there is a widespread belief that artificial general intelligence (AGI) -- or even superhuman AI -- is imminent, complex problems in expert domains are far from being solved.…
OCALM: Object-Centric Assessment with Language Models
Timo Kaufmann, Jannis Blüml, Antonia Wüst +3
Properly defining a reward signal to efficiently train a reinforcement learning (RL) agent is a challenging task. Designing balanced objective functions from which a desired behavi…
HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning
Quentin Delfosse, Jannis Blüml, Bjarne Gregori +1
Artificial agents' adaptability to novelty and alignment with intended behavior is crucial for their effective deployment. Reinforcement learning (RL) leverages novelty as a means…
Amplifying Exploration in Monte-Carlo Tree Search by Focusing on the Unknown
Cedric Derstroff, Jannis Brugger, Jannis Blüml +3
Monte-Carlo tree search (MCTS) is an effective anytime algorithm with a vast amount of applications. It strategically allocates computational resources to focus on promising segmen…
Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess
Felix Helfenstein, Johannes Czech, Jannis Blüml +2
In games like chess, strategy evolves dramatically across distinct phases - the opening, middlegame, and endgame each demand different forms of reasoning and decision-making. Yet,…
From Images to Connections: Can DQN with GNNs learn the Strategic Game of Hex?
Yannik Keller, Jannis Blüml, Gopika Sudhakaran +1
The gameplay of strategic board games such as chess, Go and Hex is often characterized by combinatorial, relational structures -- capturing distinct interactions and non-local patt…